MCPcopy
hub / github.com/huggingface/transformers / BltTransformerLayer

Class BltTransformerLayer

src/transformers/models/blt/modular_blt.py:289–296  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

287
288
289class BltTransformerLayer(MllamaSelfAttentionDecoderLayer):
290 def __init__(self, config, layer_idx: int):
291 super().__init__()
292
293 self.self_attn = BltSelfAttention(config=config, layer_idx=layer_idx)
294 self.mlp = BltMLP(config)
295 self.input_layernorm = BltRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
296 self.post_attention_layernorm = BltRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
297
298
299class BltSelfAttention(MllamaTextSelfAttention):

Callers 4

__init__Method · 0.70
__init__Method · 0.70
__init__Method · 0.70
__init__Method · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected